© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59186
    Prev
    Next
    INDEX
    Explanations

    HTML list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.95
    巴西
    -0.93
     déput
    -0.90
     Since
    -0.89
    釧
    -0.87
    Since
    -0.86
     bring
    -0.84
    Different
    -0.83
     After
    -0.82
    ʚ
    -0.82
    POSITIVE LOGITS
     li
    1.00
    Li
    1.00
     Li
    0.96
    li
    0.89
    纔
    0.85
    してみてください
    0.85
    lli
    0.85
     takich
    0.85
    ccas
    0.84
     girasol
    0.82
    Activations Density 0.006%

    No Known Activations